Journal of integrative bioinformatics: A ViTUNeT-based model using YOLOv8 for efficient LVNC diagnosis and automatic cleaning of dataset

de Haro, Salvador; Bernabé, Gregorio; García, José Manuel; González-Férez, Pilar

Bibliographic data

fullscreen: A ViTUNeT-based model using YOLOv8 for efficient LVNC diagnosis and automatic cleaning of dataset / de Haro, Salvador (CC BY)

Access restriction

There is no access restriction for this record.

Copyright

CC BY: Attribution 4.0 International. You can find more information here.

Periodical

Title:: Journal of integrative bioinformatics

Publication:: Berlin: Walter de Gruyter GmbH

Note:: Gesehen am 19.06.2020; Open Access; Namensnennung 4.0 International; 355!URL mit zLF gelöscht(26-07-17)

Scope:: Online-Ressource

ISSN:: 1613-4516

ZDB-ID:: 2147212-9

VÖBB-Katalog:: 35278163

Keywords:: Zeitschrift

Classification:: Naturwissenschaften; Informatik

Collection:: Naturwissenschaften; Informatik

Copyright:: Rights reserved

Accessibility:: Free Access

Article

Author:: de Haro, Salvador; Bernabé, Gregorio; García, José Manuel; González-Férez, Pilar

Title:: A ViTUNeT-based model using YOLOv8 for efficient LVNC diagnosis and automatic cleaning of dataset

Publication:: Berlin: Walter de Gruyter GmbH, 2025

Language:: English

Information:: Abstract: Left ventricular non-compaction is a cardiac condition marked by excessive trabeculae in the left ventricle’s inner wall. Although various methods exist to measure these structures, the medical community still lacks consensus on the best approach. Previously, we developed DL-LVTQ, a tool based on a UNet neural network, to quantify trabeculae in this region. In this study, we expand the dataset to include new patients with Titin cardiomyopathy and healthy individuals with fewer trabeculae, requiring retraining of our models to enhance predictions. We also propose ViTUNeT, a neural network architecture combining U-Net and Vision Transformers to segment the left ventricle more accurately. Additionally, we train a YOLOv8 model to detect the ventricle and integrate it with ViTUNeT model to focus on the region of interest. Results from ViTUNet and YOLOv8 are similar to DL-LVTQ, suggesting dataset quality limits further accuracy improvements. To test this, we analyze MRI images and develop a method using two YOLOv8 models to identify and remove problematic images, leading to better results. Combining YOLOv8 with deep learning networks offers a promising approach for improving cardiac image analysis and segmentation.

Scope:: Online-Ressource

Note:: Open Access; Archivierung/Langzeitarchivierung gewährleistet

Keywords:: data analysis ; image detection ; left ventricular non-compaction diagnosis ; medical imaging ; convolutional neural networks

Classification:: Naturwissenschaften; Informatik; Medizin

URN:: urn:nbn:de:101:1-2510300244028.176598050144

Collection:: Naturwissenschaften; Informatik; Medizin

Copyright:: CC BY

Accessibility:: Free Access

fullscreen: A ViTUNeT-based model using YOLOv8 for efficient LVNC diagnosis and automatic cleaning of dataset / de Haro, Salvador (CC BY)

Access restriction

There is no access restriction for this record.

Copyright

CC BY: Attribution 4.0 International. You can find more information here.

Access restriction

Copyright

Periodical

Article

Table of contents

Downloads

Full record

Image fragment

Formats and links

Links

Cite

Full record

Citation recommendation

Search results

fullscreen: A ViTUNeT-based model using YOLOv8 for efficient LVNC diagnosis and automatic cleaning of dataset / de Haro, Salvador (CC BY) Access restriction There is no access restriction for this record. Copyright CC BY: Attribution 4.0 International. You can find more information here.

Access restriction

Copyright

Table of contents

Image fragment

fullscreen: A ViTUNeT-based model using YOLOv8 for efficient LVNC diagnosis and automatic cleaning of dataset / de Haro, Salvador (CC BY)

Access restriction

There is no access restriction for this record.

Copyright

CC BY: Attribution 4.0 International. You can find more information here.